From: Longjun Tang <[email protected]> The backend raises an interrupt after adding buffers to the used ring, and the hypervisor injects it. If one is lost (e.g., a transient KVM failure), NAPI will not be scheduled and the driver stops consuming buffers. The ring eventually fills up, the backend stops notifying, and the queue is left permanently stuck.
Add a per-device watchdog that scans the RX queues once per second and detects a queue that has a non-zero backlog while making no consumption progress and receiving no new interrupt for rx_watchdog_timeo seconds (default 5, 0 disables it). On detection, reschedule NAPI. Signed-off-by: Longjun Tang <[email protected]> --- drivers/net/virtio_net.c | 104 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 104 insertions(+) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index dd2c41ef6fbe..ec7c248080c5 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -36,6 +36,10 @@ module_param(csum, bool, 0444); module_param(gso, bool, 0444); module_param(napi_tx, bool, 0644); +/* RX queue stall timeout in seconds; 0 disables the watchdog. */ +static unsigned int rx_watchdog_timeo = 5; +module_param(rx_watchdog_timeo, uint, 0644); + #define VIRTIO_OFFLOAD_MAP_MIN 46 #define VIRTIO_OFFLOAD_MAP_MAX 47 #define VIRTIO_FEATURES_MAP_MIN 65 @@ -318,6 +322,13 @@ struct send_queue { dma_addr_t xsk_hdr_dma_addr; }; +struct virtnet_rq_watchdog { + u16 last_used; + u16 calls; + unsigned long jiffies; + bool stalled; +}; + /* Internal representation of a receive virtqueue */ struct receive_queue { /* Virtqueue associated with this receive_queue */ @@ -332,6 +343,9 @@ struct receive_queue { /* The number of rx notifications */ u16 calls; + /* RX watchdog state. */ + struct virtnet_rq_watchdog watchdog; + /* Is dynamic interrupt moderation enabled? */ bool dim_enabled; @@ -443,6 +457,9 @@ struct virtnet_info { /* Work struct for setting rx mode */ struct work_struct rx_mode_work; + /* RX watchdog timer for stuck detection */ + struct timer_list rx_watchdog; + /* Does the affinity hint is set for virtqueues? */ bool affinity_hint_set; @@ -3067,6 +3084,80 @@ static int virtnet_poll(struct napi_struct *napi, int budget) return received; } +/* + * An RX queue is stalled if it has a backlog but makes no progress and + * gets no new interrupt for rx_watchdog_timeo seconds, usually because + * an interrupt was lost. Mark it stalled and reschedule NAPI to drain + * the ring, refill the buffers. + */ +static void virtnet_rx_watchdog(struct timer_list *t) +{ + struct virtnet_info *vi = timer_container_of(vi, t, rx_watchdog); + unsigned long timeout = rx_watchdog_timeo * HZ; + int i; + + if (!rx_watchdog_timeo) + return; + + for (i = 0; i < vi->curr_queue_pairs; i++) { + struct receive_queue *rq = &vi->rq[i]; + u16 last_used = virtqueue_get_last_used_idx(rq->vq); + u16 calls = rq->calls; + bool backlog = virtqueue_poll(rq->vq, last_used); + bool progress = last_used != rq->watchdog.last_used; + + if (!backlog || progress || calls != rq->watchdog.calls) { + rq->watchdog.last_used = last_used; + rq->watchdog.calls = calls; + rq->watchdog.jiffies = jiffies; + continue; + } + + if (time_after(jiffies, rq->watchdog.jiffies + timeout)) { + unsigned int stall_ms = + jiffies_to_msecs(jiffies - rq->watchdog.jiffies); + + netdev_warn(vi->dev, + "RX queue %u stalled for %u ms, rescheduling NAPI\n", + i, stall_ms); + + rq->watchdog.stalled = true; + virtqueue_napi_schedule(&rq->napi, rq->vq); + + /* Rate-limit to one event per timeout. */ + rq->watchdog.jiffies = jiffies; + } + } + + mod_timer(&vi->rx_watchdog, jiffies + HZ); +} + +static void virtnet_rx_watchdog_init_queue(struct receive_queue *rq) +{ + rq->watchdog.last_used = virtqueue_get_last_used_idx(rq->vq); + rq->watchdog.calls = rq->calls; + rq->watchdog.jiffies = jiffies; + rq->watchdog.stalled = false; +} + +static void virtnet_rx_watchdog_start(struct virtnet_info *vi) +{ + int i; + + if (!rx_watchdog_timeo) + return; + + for (i = 0; i < vi->curr_queue_pairs; i++) + virtnet_rx_watchdog_init_queue(&vi->rq[i]); + + mod_timer(&vi->rx_watchdog, jiffies + HZ); +} + +static void virtnet_rx_watchdog_stop(struct virtnet_info *vi) +{ + timer_delete_sync(&vi->rx_watchdog); +} + static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) { virtnet_napi_tx_disable(&vi->sq[qp_index]); @@ -3230,6 +3321,8 @@ static int virtnet_open(struct net_device *dev) netif_carrier_on(dev); } + virtnet_rx_watchdog_start(vi); + return 0; err_enable_qp: @@ -3759,6 +3852,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) struct virtio_net_rss_config_trailer old_rss_trailer; struct net_device *dev = vi->dev; struct scatterlist sg; + u16 old_queue_pairs = vi->curr_queue_pairs; if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ)) return 0; @@ -3816,7 +3910,14 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) if (vi->has_rss) vi->rss_trailer.max_tx_vq = cpu_to_le16(queue_pairs); succ: + if (dev->flags & IFF_UP) { + /* Init new queues */ + for (int i = old_queue_pairs; i < queue_pairs; i++) + virtnet_rx_watchdog_init_queue(&vi->rq[i]); + } + vi->curr_queue_pairs = queue_pairs; + if (dev->flags & IFF_UP) { local_bh_disable(); for (int i = 0; i < vi->curr_queue_pairs; ++i) @@ -3832,6 +3933,8 @@ static int virtnet_close(struct net_device *dev) struct virtnet_info *vi = netdev_priv(dev); int i; + virtnet_rx_watchdog_stop(vi); + /* Prevent the config change callback from changing carrier * after close */ @@ -6900,6 +7003,7 @@ static int virtnet_probe(struct virtio_device *vdev) INIT_WORK(&vi->config_work, virtnet_config_changed_work); INIT_WORK(&vi->rx_mode_work, virtnet_rx_mode_work); disable_work(&vi->rx_mode_work); + timer_setup(&vi->rx_watchdog, virtnet_rx_watchdog, 0); if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) { vi->mergeable_rx_bufs = true; -- 2.51.0
